Polarity Classification Tool for Sentiment Analysis in Malay Language

The popularity of the social media channels has increased the interest among researchers in the sentiment analysis (SA) area. One aspect of the SA research is the determination of the polarity of the comments in the social media, i.e. positive, negative, and neutral. However, there is a scarcity of...

Full description

Bibliographic Details
Main Authors:	Awang Abu Bakar, Normi Sham, RAHMAT, ROS AZIEHAN, UTHMAN, UMAR FARUQ
Format:	Article
Language:	English English
Published:	2019
Subjects:	T10.5 Communication of technical information
Online Access:	http://irep.iium.edu.my/75242/ http://irep.iium.edu.my/75242/ http://irep.iium.edu.my/75242/1/Polarity%20Classification%20Tool%20for%20Sentiment%20Analysis%20in%20Malay%20Language.pdf http://irep.iium.edu.my/75242/7/75242_Polarity%20classification%20tool%20for%20sentiment%20analysis%20in%20Malay%20language_Scopus.pdf

id	iium-75242
recordtype	eprints
spelling	iium-752422019-11-24T13:35:29Z http://irep.iium.edu.my/75242/ Polarity Classification Tool for Sentiment Analysis in Malay Language Awang Abu Bakar, Normi Sham RAHMAT, ROS AZIEHAN UTHMAN, UMAR FARUQ T10.5 Communication of technical information The popularity of the social media channels has increased the interest among researchers in the sentiment analysis (SA) area. One aspect of the SA research is the determination of the polarity of the comments in the social media, i.e. positive, negative, and neutral. However, there is a scarcity of Malay sentiment analysis tools because most of the work in the literature discuss the polarity classification tool in English. This paper presents the development of a polarity classification tool called Malay Polarity Classification Tool (MaCT). This tool is developed based on the AFINN sentiment lexicon for English language. We have attempted to translate each word in AFINN to its Malay equivalent and later, use the lexicon to collect the sentiment data from Twitter. The Twitter data are then classified into positive, negative, and neutral. For the validation purpose, we collect 400 positive tweets, 400 negative tweets, and 200 neutral tweets, and later, run the tweets through our sentiment lexicon and found 90% score for precision, recall and accuracy. Our main contribution in the research is the new AFINN translation for Malay language and also the classification of the sentiment data. 2019-09-01 Article PeerReviewed application/pdf en http://irep.iium.edu.my/75242/1/Polarity%20Classification%20Tool%20for%20Sentiment%20Analysis%20in%20Malay%20Language.pdf application/pdf en http://irep.iium.edu.my/75242/7/75242_Polarity%20classification%20tool%20for%20sentiment%20analysis%20in%20Malay%20language_Scopus.pdf Awang Abu Bakar, Normi Sham and RAHMAT, ROS AZIEHAN and UTHMAN, UMAR FARUQ (2019) Polarity Classification Tool for Sentiment Analysis in Malay Language. IAES International Journal of Artificial Intelligence (IJ-AI), 8 (3). pp. 258-263. ISSN 2252-8938 10.11591/ijai.v8.i3
repository_type	Digital Repository
institution_category	Local University
institution	International Islamic University Malaysia
building	IIUM Repository
collection	Online Access
language	English English
topic	T10.5 Communication of technical information
spellingShingle	T10.5 Communication of technical information Awang Abu Bakar, Normi Sham RAHMAT, ROS AZIEHAN UTHMAN, UMAR FARUQ Polarity Classification Tool for Sentiment Analysis in Malay Language
description	The popularity of the social media channels has increased the interest among researchers in the sentiment analysis (SA) area. One aspect of the SA research is the determination of the polarity of the comments in the social media, i.e. positive, negative, and neutral. However, there is a scarcity of Malay sentiment analysis tools because most of the work in the literature discuss the polarity classification tool in English. This paper presents the development of a polarity classification tool called Malay Polarity Classification Tool (MaCT). This tool is developed based on the AFINN sentiment lexicon for English language. We have attempted to translate each word in AFINN to its Malay equivalent and later, use the lexicon to collect the sentiment data from Twitter. The Twitter data are then classified into positive, negative, and neutral. For the validation purpose, we collect 400 positive tweets, 400 negative tweets, and 200 neutral tweets, and later, run the tweets through our sentiment lexicon and found 90% score for precision, recall and accuracy. Our main contribution in the research is the new AFINN translation for Malay language and also the classification of the sentiment data.
format	Article
author	Awang Abu Bakar, Normi Sham RAHMAT, ROS AZIEHAN UTHMAN, UMAR FARUQ
author_facet	Awang Abu Bakar, Normi Sham RAHMAT, ROS AZIEHAN UTHMAN, UMAR FARUQ
author_sort	Awang Abu Bakar, Normi Sham
title	Polarity Classification Tool for Sentiment Analysis in Malay Language
title_short	Polarity Classification Tool for Sentiment Analysis in Malay Language
title_full	Polarity Classification Tool for Sentiment Analysis in Malay Language
title_fullStr	Polarity Classification Tool for Sentiment Analysis in Malay Language
title_full_unstemmed	Polarity Classification Tool for Sentiment Analysis in Malay Language
title_sort	polarity classification tool for sentiment analysis in malay language
publishDate	2019
url	http://irep.iium.edu.my/75242/ http://irep.iium.edu.my/75242/ http://irep.iium.edu.my/75242/1/Polarity%20Classification%20Tool%20for%20Sentiment%20Analysis%20in%20Malay%20Language.pdf http://irep.iium.edu.my/75242/7/75242_Polarity%20classification%20tool%20for%20sentiment%20analysis%20in%20Malay%20language_Scopus.pdf
first_indexed	2023-09-18T21:46:27Z
last_indexed	2023-09-18T21:46:27Z
_version_	1777413482482761728

Polarity Classification Tool for Sentiment Analysis in Malay Language

Similar Items